© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 29598
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ap" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.14
    0.8%
    164
    +0.14
    0.8%
    432
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    432
    +0.14
    0.05
    128
    +0.14
    0.03
    164
    +0.13
    0.03
    Negative Logits
    Ĥ
    -3.46
    Ń
    -3.27
    ¿
    -3.14
    ¼
    -3.09
    ĵ
    -3.00
    ´
    -2.95
    ķ
    -2.87
    Īĺ
    -2.87
    ¿½
    -2.84
    Ļª
    -2.84
    POSITIVE LOGITS
    shots
    1.65
    caster
    1.61
    witz
    1.54
    orte
    1.49
    iary
    1.45
    onin
    1.44
    itol
    1.42
    arant
    1.41
    bilt
    1.40
    ulous
    1.38
    Activations Density 5.065%

    No Known Activations